A sentry warning method and system based on image recognition

Abstract

The present invention provides a sentinel warning method and system based on image recognition, which belongs to the field of image processing technology. Specifically, the method and system include: obtaining the remaining power and safe power threshold of a vehicle's on-board battery, and determining the safe value of the on-board battery in combination with cycle data; determining the problem probability of the parking period by using parked vehicles in sentinel warning mode during the parking period at the current location within the most recent preset time and historical alarm data; determining the image monitoring frequency of the sentinel warning mode during the parking period based on the safe value of the on-board battery, the problem probability and the historical traffic congestion; performing vehicle environment monitoring based on the image monitoring frequency to obtain an environmental image; and dynamically adjusting the image monitoring frequency of the sentinel warning mode based on the recognition result of the image recognition of the environmental image during the parking period, thereby further improving the safety of the vehicle.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a sentry warning method and system based on image recognition. Background Art

[0002] Existing smart vehicles are often equipped with surveillance cameras and sentry modes. Through the settings of the surveillance cameras and sentry mode, videos will be recorded and pushed to users when the vehicle experiences abnormal vibrations. However, at the same time, the application of sentry mode will cause a large amount of power loss. In severe cases, it may even cause the vehicle's on-board battery to run out of power and be unable to start normally. Therefore, how to adaptively activate and issue warnings in sentry mode has become a technical problem that needs to be solved urgently.

[0003] To address the above technical issues, the invention patent CN202211493729.8, "Sentinel Mode Recommendation Method, Apparatus, Device, and Medium," presets sentinel mode recommendation conditions so that sentinel mode is recommended when the conditions are met, while there is no need to recommend or enable sentinel mode when the conditions are not met. This achieves adaptive recommendation and activation of sentinel mode, but it still has the following technical issues:

[0004] The existing technical solutions ignore the activation of sentinel mode based on the real-time status of the vehicle's battery. Specifically, when the vehicle's battery has different remaining capacities, the use of sentinel mode will cause the vehicle to have a significantly different risk of power failure. Therefore, if the sentinel mode cannot be activated based on the remaining capacity of the vehicle's battery, the safety of the vehicle cannot be guaranteed while ensuring the safety of the vehicle's battery.

[0005] The existing technical solutions ignore the selection of differentiated sentinel warning modes based on the recognition results of image recognition. Specifically, for different monitoring locations, there are certain differences in the number of vehicles and pedestrians at different times, and the probability of scratches occurring therein also varies to a certain extent. Therefore, if the differentiated sentinel warning modes cannot be selected based on the above factors, it is impossible to ensure the safety of the vehicle while ensuring the safety of the vehicle's battery.

[0006] In response to the above technical problems, the present invention provides a sentinel warning method and system based on image recognition. Summary of the Invention

[0007] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0008] According to one aspect of the present invention, a sentinel warning method based on image recognition is provided.

[0009] A sentry warning method based on image recognition, characterized by specifically comprising:

[0010] S1 obtains the remaining power and safety power threshold of the vehicle's onboard battery, and determines the safety value of the onboard battery in combination with the cycle data. When the safety value meets the requirements, proceeds to the next step;

[0011] S2 determines the parking period corresponding to the current time, and determines the historical traffic busyness of the parking period based on the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates. Based on the usage safety value, determines whether the historical traffic busyness meets the requirements. If so, proceed to the next step; if not, perform vehicle environment monitoring in a real-time sentinel warning mode;

[0012] S3 determines the problem probability of a parking period at the current location using the number of vehicles parked in the sentinel warning mode within a recent preset period and historical alarm data, and determines the image monitoring frequency of the sentinel warning mode during the parking period based on the vehicle battery safety value, the problem probability, and historical traffic congestion.

[0013] S4 performs vehicle environment monitoring based on the image monitoring frequency to obtain an environmental image, and dynamically adjusts the image monitoring frequency of the sentry warning mode based on a recognition result of the environmental image during the parking period.

[0014] The beneficial effects of the present invention are:

[0015] 1. By combining the remaining power of the vehicle's on-board battery and the safety power threshold and using cycle data to determine the safety value of the on-board battery, the difference in the safety power threshold due to the difference in standby power consumption of different vehicles is taken into account, while the difference in the degree of aging of the on-board battery caused by the use of cycle data is taken into account, thereby achieving an accurate assessment of the safety status of the vehicle battery based on the remaining power, and also laying the foundation for further realizing the differentiated setting of the sentinel warning mode.

[0016] 2. By determining the image monitoring frequency of the sentinel warning mode during parking periods based on the safety value of the on-board battery, the problem probability, and the historical traffic congestion, we take into account the safety status of the on-board battery, as well as the historical problem conditions, pedestrian and vehicle traffic during different parking periods. This ensures the safety of the battery while also ensuring the differences in the demand for the sentinel warning mode from the perspectives of different problem probabilities and traffic.

[0017] 3. The image monitoring frequency of the sentry warning mode is dynamically adjusted by the recognition results of the image recognition based on the environmental image of the parking period, thereby realizing the dynamic adjustment of the image monitoring frequency of the sentry warning mode based on the difference in the flow of people in the recognition results of the image recognition. On the basis of ensuring the reliability of monitoring, unnecessary energy loss is also reduced.

[0018] A further technical solution is that the safety power threshold is determined based on the power consumption of the vehicle within a specified period of time during parking and the power consumption required for starting the vehicle.

[0019] A further technical solution is that the usage cycle data includes the number of usage cycles of the vehicle-mounted battery and the battery charge and discharge depths at different usage cycle numbers.

[0020] A further technical solution is that when the usage safety value does not meet the requirements, the sentry warning mode is temporarily stopped and it is determined that the vehicle environment monitoring cannot be performed.

[0021] A further technical solution is that the method for determining the use safety value of the vehicle-mounted battery is:

[0022] The deviation between the remaining power of the vehicle's onboard battery and a safety power threshold is used as a safety remaining power, and the power attenuation rate of the vehicle's onboard battery at different charge and discharge cycles is determined based on the usage cycle data of the vehicle's onboard battery.

[0023] Determining an attenuation evaluation value of the on-board battery based on an average value of the battery charge attenuation rate and the number of charge and discharge cycles in which the battery charge attenuation rate is greater than a preset attenuation rate, and determining whether the on-board battery has an aging problem based on the attenuation evaluation value. If so, proceeding to the next step; if not, determining a safety value for the on-board battery based on the safe remaining power;

[0024] An aging assessment value of the on-board battery is determined based on the number of usage cycles of the on-board battery and the charge and discharge depths and attenuation assessment values ​​at different usage cycles, and the safe remaining power is corrected based on the aging assessment value to obtain a safety value for the on-board battery.

[0025] A further technical solution is that the method for determining the traffic busyness during the parking period is:

[0026] The flow evaluation value of the current location during the parking periods on different dates is determined by the vehicle flow and pedestrian flow during the parking periods on different dates at the current location, and the maximum value of the flow evaluation value is used as a reference evaluation value. The number of dates whose deviation from the reference evaluation value is less than a preset deviation is used to determine whether the accuracy of the reference evaluation value meets the requirements. If so, the reference evaluation value is used as the flow busyness of the parking period. If not, the flow busyness of the parking period is determined by the average value of the reference evaluation value.

[0027] A further technical solution is to determine whether the traffic congestion meets the requirement based on the usage safety value, specifically including:

[0028] The busyness threshold of the vehicle in different parking periods is determined by using the safety value, and when the traffic busyness is greater than the busyness threshold, it is determined that the traffic busyness does not meet the requirement.

[0029] A further technical solution is that the method for determining the image monitoring frequency is:

[0030] Determining the basic image monitoring frequency of the sentinel warning mode during the parking period based on the safety value of the on-board battery, and judging whether the problem probability is greater than a preset probability value; if so, determining the image monitoring frequency of the sentinel warning mode based on the basic image monitoring frequency; if not, proceeding to the next step;

[0031] The frequency correction amount is determined by the problem probability and the historical traffic busyness, and the image monitoring frequency of the sentinel warning mode during the parking period is determined based on the product of the frequency correction amount and the basic image monitoring frequency.

[0032] On the other hand, the present invention provides a sentinel warning system based on image recognition, which adopts the above-mentioned sentinel warning method based on image recognition and is characterized by specifically comprising:

[0033] Battery evaluation module, busyness evaluation module, warning mode determination module, warning mode adjustment module;

[0034] The battery evaluation module is responsible for obtaining the remaining power and safe power threshold of the vehicle's onboard battery, and determining the safety value of the onboard battery in combination with the cycle data;

[0035] The busyness evaluation module is responsible for determining the parking period corresponding to the current moment, and determining the historical traffic busyness of the parking period based on the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates;

[0036] The warning mode determination module is responsible for determining the problem probability of the parking period by using the vehicles parked in the sentinel warning mode at the current location within the most recent preset parking period and historical alarm data, and determining the image monitoring frequency of the sentinel warning mode during the parking period based on the safety value of the vehicle battery, the problem probability, and the historical traffic congestion;

[0037] The warning mode adjustment module is responsible for performing vehicle environment monitoring based on the image monitoring frequency to obtain an environmental image, and dynamically adjusting the image monitoring frequency of the sentry warning mode based on the recognition result of the environmental image during the parking period.

[0038] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0041] Figure 1 It is a flow chart of a sentinel warning method based on image recognition;

[0042] Figure 2 It is a flow chart of a method for determining a safe value of a vehicle battery;

[0043] Figure 3 This is a flow chart of another possible method for determining the safety value of a vehicle battery;

[0044] Figure 4 is a flow chart of a method for determining a problem probability of a parking period;

[0045] Figure 5 is a flow chart of a method for determining an image monitoring frequency;

[0046] Figure 6 This is a framework diagram of a sentinel warning system based on image recognition; DETAILED DESCRIPTION

[0047] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0048] Problems with existing technical solutions:

[0049] The existing sentry warning mode often monitors in real time and automatically starts recording when the vehicle experiences abnormal vibrations, etc., which not only fails to take into account the excessive use of the sentry warning mode caused by differences in the status of the vehicle's on-board battery, thereby causing the on-board battery to run low, but also fails to take into account historical alarm events such as vehicle scratches and thefts that occur at different parking locations during different parking periods, making it impossible to achieve dynamic adjustment of the sentry warning mode.

[0050] In order to solve the above technical problems, the following technical means are mainly adopted:

[0051] First, the safety battery remaining of the vehicle battery is determined based on the remaining power of the vehicle battery and the safety power threshold, and the aging coefficient is determined based on the ratio of the number of use cycles of the vehicle battery to the number of life cycles. The use safety value is determined by multiplying the ratio of the safety battery remaining to the rated capacity of the vehicle battery by the aging coefficient. When the use safety value does not meet the requirements, the sentry warning module is not turned on. When the use safety value meets the requirements, the next step is entered;

[0052] Then, the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates are determined based on the parking period corresponding to the current moment, and the historical traffic busyness of the parking period is determined based on the average value of the historical vehicle flow and historical pedestrian flow of the parking periods on different dates and the ratio of the preset vehicle flow and pedestrian flow. When the historical traffic busyness is large, vehicle environment monitoring is performed through the real-time sentinel warning mode. When the historical traffic busyness is small, the problem probability of the parking period is determined using the parked vehicles in the sentinel warning mode during the parking period at the current location within the most recent preset time and the historical alarm data. Specifically, the problem probability of the parking period is determined based on the ratio of the historical alarm data to the parked vehicles in the sentinel warning mode, and the image monitoring frequency of the sentinel warning mode of the parking period is determined based on the safety value of the vehicle battery, the problem probability and the minimum value of the preset image monitoring frequency corresponding to the historical traffic busyness.

[0053] Finally, vehicle environment monitoring is performed based on the image monitoring frequency to obtain an environmental image, and the image monitoring frequency of the sentinel warning mode is dynamically adjusted based on the recognition result of the image recognition of the environmental image during the parking period. Specifically, when an alarm event exists in the recognition result of the image recognition of the environmental image during the parking period, vehicle environment monitoring is performed through the real-time sentinel warning mode. When there is no alarm event, the image monitoring frequency is dynamically adjusted based on the vehicle flow and pedestrian flow in the recognition result of the image recognition of the environmental image during the parking period.

[0054] The following will be elaborated in detail from two perspectives: system type embodiments and method type embodiments.

[0055] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a sentry warning method based on image recognition is provided, which is characterized by specifically including:

[0056] S1 obtains the remaining power and safety power threshold of the vehicle's onboard battery, and determines the safety value of the onboard battery in combination with the cycle data. When the safety value meets the requirements, proceeds to the next step;

[0057] Furthermore, the safety power threshold is determined based on the power consumption of the vehicle within a specified period of time during parking and the power consumption required for starting the vehicle.

[0058] Specifically, the usage cycle data includes the number of usage cycles of the vehicle-mounted battery and the battery charge and discharge depths at different numbers of usage cycles.

[0059] In one possible embodiment, Figure 2 As shown, the method for determining the safety value of the vehicle-mounted battery in step S1 is:

[0060] S11 takes the deviation between the remaining power of the vehicle's onboard battery and the safety power threshold as a safety remaining power, and determines whether the safety remaining power meets the requirement. If so, proceeds to the next step; if not, determines the safety value of the vehicle's onboard battery based on the safety remaining power;

[0061] S12 obtains usage cycle data of the vehicle's onboard battery, and determines the number of usage cycles of the vehicle's onboard battery based on the usage cycle data, and determines whether the vehicle's onboard battery has an aging problem based on the number of usage cycles. If so, proceeds to step S14; if not, proceeds to the next step;

[0062] S13 determines the battery attenuation rate of the on-board battery at different charge and discharge cycles based on the usage cycle data of the on-board battery, and determines the attenuation evaluation value of the on-board battery based on the average value of the battery attenuation rate of the on-board battery and the number of charge and discharge cycles at which the battery attenuation rate is greater than a preset attenuation rate. It is determined whether the on-board battery has an aging problem based on the attenuation evaluation value. If so, the process proceeds to step S14. If not, the use safety value of the on-board battery is determined based on the safe remaining power.

[0063] In one possible embodiment, the attenuation evaluation value of the vehicle battery is determined based on the product of the average value of the battery charge attenuation rate of the vehicle battery and the ratio of the number of charge and discharge cycles in which the battery charge attenuation rate is greater than the preset attenuation rate to the number of all charge and discharge cycles.

[0064] S14 determines an aging assessment value of the vehicle battery based on the number of usage cycles of the vehicle battery and the charge and discharge depths and attenuation assessment values ​​at different usage cycles, and corrects the safe remaining power based on the aging assessment value to obtain a safety value for the vehicle battery.

[0065] Specifically, first, the number of usage cycles with a higher charge and discharge depth is determined according to the charge and discharge depths of different usage cycles, then the charge and discharge cycle aging coefficient is determined according to the number of usage cycles with a higher charge and discharge depth and the ratio of the number of usage cycles to the service life of the vehicle battery, and finally the aging evaluation value of the vehicle battery is determined according to the weight of the charge and discharge aging coefficient and the attenuation evaluation value.

[0066] It is understandable that when the usage safety value does not meet the requirements, the sentry warning mode is temporarily stopped and it is determined that vehicle environment monitoring cannot be performed.

[0067] In another possible embodiment, Figure 3 As shown, the method for determining the safety value of the vehicle-mounted battery in step S1 is:

[0068] The deviation between the remaining power of the vehicle's onboard battery and a safety power threshold is used as a safety remaining power, and the power attenuation rate of the vehicle's onboard battery at different charge and discharge cycles is determined based on the usage cycle data of the vehicle's onboard battery.

[0069] Determining an attenuation evaluation value of the on-board battery based on an average value of the battery charge attenuation rate and the number of charge and discharge cycles in which the battery charge attenuation rate is greater than a preset attenuation rate, and determining whether the on-board battery has an aging problem based on the attenuation evaluation value. If so, proceeding to the next step; if not, determining a safety value for the on-board battery based on the safe remaining power;

[0070] An aging assessment value of the on-board battery is determined based on the number of usage cycles of the on-board battery and the charge and discharge depths and attenuation assessment values ​​at different usage cycles, and the safe remaining power is corrected based on the aging assessment value to obtain a safety value for the on-board battery.

[0071] S2 determines the parking period corresponding to the current time, and determines the historical traffic busyness of the parking period based on the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates. Based on the usage safety value, determines whether the historical traffic busyness meets the requirements. If so, proceed to the next step; if not, perform vehicle environment monitoring in a real-time sentinel warning mode;

[0072] Specifically, the method for determining the traffic busyness during the parking period is:

[0073] The flow evaluation value of the current location during the parking periods on different dates is determined by the vehicle flow and pedestrian flow during the parking periods on different dates at the current location, and the maximum value of the flow evaluation value is used as a reference evaluation value. The number of dates whose deviation from the reference evaluation value is less than a preset deviation is used to determine whether the accuracy of the reference evaluation value meets the requirements. If so, the reference evaluation value is used as the flow busyness of the parking period. If not, the flow busyness of the parking period is determined by the average value of the reference evaluation value.

[0074] It should be further explained that determining whether the traffic congestion meets the requirement based on the usage safety value specifically includes:

[0075] The busyness threshold of the vehicle in different parking periods is determined by using the safety value, and when the traffic busyness is greater than the busyness threshold, it is determined that the traffic busyness does not meet the requirement.

[0076] S3 determines the problem probability of a parking period at the current location using the number of vehicles parked in the sentinel warning mode within a recent preset period and historical alarm data, and determines the image monitoring frequency of the sentinel warning mode during the parking period based on the vehicle battery safety value, the problem probability, and historical traffic congestion.

[0077] In one possible embodiment, Figure 4 As shown, the method for determining the problem probability of the parking period in the above step S2 is:

[0078] S21: Parked vehicles in sentry mode at the current location within a recent preset parking period are used as parking monitoring vehicles, and a historical alarm count of the parking monitoring vehicle is determined based on historical alarm data of the parking monitoring vehicle. Whether the historical alarm count is within a preset required count range is determined based on the number of parking monitoring vehicles. If so, a problem probability of the parking period is determined based on the historical alarm count and the number of parking monitoring vehicles. If not, proceed to the next step.

[0079] S22: calculating the percentage of dates on which the parking monitoring vehicle has historical alarm data within a preset time period based on the historical alarm data of the parking monitoring vehicle, and determining whether the percentage of dates on which the historical alarm data has historical alarm data is less than a preset ratio; if so, determining the probability of a problem in the parking period based on the percentage of dates on which the parking monitoring vehicle has historical alarm data within the preset time period; if not, proceeding to the next step;

[0080] S23: Dates on which the parked monitoring vehicle has historical alarm data within a preset time period are used as alarm dates, and problem assessment amounts are determined for different alarm dates based on the number of parked monitoring vehicles and the number of historical alarms on different alarm dates, and serious problem dates and general problem dates are determined among the alarm dates based on the problem assessment amounts;

[0081] S24 obtains the number and proportion of serious problem dates in the alarm dates, and determines the problem probability of the parking period based on the number of alarm dates and the problem evaluation amount.

[0082] In another possible embodiment, the method for determining the problem probability of the parking period in step S2 is:

[0083] Taking a parked vehicle in sentry mode during a recent parking period at the current location as a parking monitoring vehicle, and determining a historical alarm count of the parking monitoring vehicle based on historical alarm data of the parking monitoring vehicle;

[0084] The date on which the parking monitoring vehicle has historical alarm data within a preset time is used as the alarm date, and the problem assessment amount of different alarm dates is determined based on the number of parking monitoring vehicles and the number of historical alarms on different alarm dates. It is determined whether there is an alarm date for which the problem assessment amount does not meet the requirements. If so, the problem probability of the parking period is determined based on the maximum value of the problem assessment amount. If not, the process proceeds to the next step.

[0085] Based on the problem evaluation amount, the serious problem date and the general problem date in the alarm date are determined, the weight of the alarm date is determined by the time distance between the alarm date and the current date, and the weight sum of the problem evaluation amount of the serious problem date is determined by the weight of the serious problem date in the alarm date and the problem evaluation amount, and it is judged whether the weight sum of the problem evaluation amount of the serious problem date in the warning date meets the requirements. If so, the problem probability of the parking period is determined by multiplying the proportion of the serious problem date in the warning date and the weight sum of the problem evaluation amount of the serious problem date. If not, proceed to the next step;

[0086] The number and proportion of serious problem dates in the alarm dates are obtained, and the problem probability of the parking period is determined based on the number of alarm dates and the problem evaluation amount.

[0087] S4 performs vehicle environment monitoring based on the image monitoring frequency to obtain an environmental image, and dynamically adjusts the image monitoring frequency of the sentry warning mode based on a recognition result of the environmental image during the parking period.

[0088] In one possible embodiment, Figure 5 As shown, the method for determining the image monitoring frequency in step S4 is:

[0089] S41 determines the basic image monitoring frequency of the sentinel warning mode during the parking period based on the safety value of the vehicle-mounted battery, and determines whether the problem probability is greater than a preset probability value. If so, determines the image monitoring frequency of the sentinel warning mode based on the basic image monitoring frequency; if not, proceeds to the next step;

[0090] S42 determines a frequency correction value based on the problem probability and the historical traffic busyness, and determines the image monitoring frequency of the sentry warning mode during the parking period based on the product of the frequency correction value and the basic image monitoring frequency.

[0091] It is understandable that the image monitoring frequency of the sentry warning mode is dynamically adjusted based on the recognition result of the environmental image during the parking period, specifically including:

[0092] determining whether there is a preset alarm event during the parking period based on the recognition result of the image recognition of the environmental image during the parking period, and if so, switching the sentinel warning mode to the real-time sentinel warning mode; if not, proceeding to the next step;

[0093] Determining an environmental image containing pedestrians or vehicles during the parking period based on the recognition result of the image recognition, and using the image as a screening environmental image; determining whether a mode switch is required based on the proportion of the screening environmental image in the environmental image; if so, switching the sentry warning mode to the real-time sentry warning mode; if not, proceeding to the next step;

[0094] Determine the pedestrian flow and vehicle flow in the screening environment image through the screening environment image, and determine whether the pedestrian flow and vehicle flow in the screening environment image meet the requirements based on the image monitoring frequency and monitoring duration of the parking period, if so, proceed to the next step; if not, switch the sentinel warning mode to the real-time sentinel warning mode;

[0095] The screening environment image is divided into a short-term screening environment image and a long-term screening environment image according to the time corresponding to the screening environment image, and the short-term traffic busyness of the parking period is determined according to the number of short-term screening environment images in the parking period and the pedestrian flow and vehicle flow in the short-term screening environment image. Whether a mode switch is required is determined according to the short-term traffic busyness. If so, the sentry warning mode is switched to the real-time sentry warning mode. If not, proceed to the next step.

[0096] The image monitoring frequency and monitoring duration of the parking period are obtained, and the real-time busyness of the parking period is determined in combination with the pedestrian and vehicle traffic in the filtered environmental image. The frequency correction amount of the image monitoring frequency of the sentinel warning mode is determined based on the real-time busyness and the short-term traffic busyness, and the image monitoring frequency of the sentinel warning mode is dynamically adjusted based on the frequency correction amount.

[0097] System Examples

[0098] On the other hand, Figure 6 As shown, the present invention provides a sentry warning system based on image recognition, which adopts the above-mentioned sentry warning method based on image recognition, and is characterized by specifically including:

[0099] Battery evaluation module, busyness evaluation module, warning mode determination module, warning mode adjustment module;

[0100] The battery evaluation module is responsible for obtaining the remaining power and safe power threshold of the vehicle's onboard battery, and determining the safety value of the onboard battery in combination with the cycle data;

[0101] The busyness evaluation module is responsible for determining the parking period corresponding to the current moment, and determining the historical traffic busyness of the parking period based on the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates;

[0102] The warning mode determination module is responsible for determining the problem probability of the parking period by using the vehicles parked in the sentinel warning mode at the current location within the most recent preset parking period and historical alarm data, and determining the image monitoring frequency of the sentinel warning mode during the parking period based on the safety value of the vehicle battery, the problem probability, and the historical traffic congestion;

[0103] The warning mode adjustment module is responsible for performing vehicle environment monitoring based on the image monitoring frequency to obtain an environmental image, and dynamically adjusting the image monitoring frequency of the sentry warning mode based on the recognition result of the environmental image during the parking period.

[0104] Based on the above embodiments, the present application achieves the following beneficial effects:

[0105] 1. By combining the remaining power of the vehicle's on-board battery and the safety power threshold and using cycle data to determine the safety value of the on-board battery, the difference in the safety power threshold due to the difference in standby power consumption of different vehicles is taken into account, while the difference in the degree of aging of the on-board battery caused by the use of cycle data is taken into account, thereby achieving an accurate assessment of the safety status of the vehicle battery based on the remaining power, and also laying the foundation for further realizing the differentiated setting of the sentinel warning mode.

[0106] 2. By determining the image monitoring frequency of the sentinel warning mode during parking periods based on the safety value of the on-board battery, the problem probability, and the historical traffic congestion, we take into account the safety status of the on-board battery, as well as the historical problem conditions, pedestrian and vehicle traffic during different parking periods. This ensures the safety of the battery while also ensuring the differences in the demand for the sentinel warning mode from the perspectives of different problem probabilities and traffic.

[0107] 3. The image monitoring frequency of the sentry warning mode is dynamically adjusted by the recognition results of the image recognition based on the environmental image of the parking period, thereby realizing the dynamic adjustment of the image monitoring frequency of the sentry warning mode based on the difference in the flow of people in the recognition results of the image recognition. On the basis of ensuring the reliability of monitoring, unnecessary energy loss is also reduced.

[0108] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0109] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A sentry warning method based on image recognition, characterized in that: Specifically include: Obtaining the remaining power and safe power threshold of the vehicle's onboard battery, and determining a safe value for the onboard battery in combination with the cycle data, and proceeding to the next step when the safe value meets the requirements; Determine the parking period corresponding to the current moment, and determine the historical traffic busyness of the parking period based on the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates. Determine whether the historical traffic busyness meets the requirements based on the usage safety value. If so, proceed to the next step. If not, perform vehicle environment monitoring through the real-time sentinel warning mode. Determining the problem probability of a parking period using vehicles parked in sentinel warning mode at the current location within a recent preset period and historical alarm data, and determining the image monitoring frequency of sentinel warning mode during the parking period based on the vehicle battery's safety value, the problem probability, and historical traffic congestion; The vehicle environment is monitored based on the image monitoring frequency to obtain an environmental image, and the image monitoring frequency of the sentry warning mode is dynamically adjusted based on a recognition result of the environmental image during the parking period.

2. The sentry warning method based on image recognition according to claim 1, characterized in that: The safety power threshold is determined based on the power consumption of the vehicle during a specified period of time while the vehicle is parked and the power consumption required for starting the vehicle.

3. The sentry warning method based on image recognition according to claim 1, characterized in that: The usage cycle data includes the usage cycle number of the vehicle-mounted battery and the battery charge and discharge depth at different usage cycle numbers.

4. The sentry warning method based on image recognition according to claim 1, characterized in that: When the usage safety value does not meet the requirement, the sentry warning mode is temporarily stopped and it is determined that the vehicle environment monitoring cannot be performed.

5. The sentry warning method based on image recognition according to claim 1, characterized in that: The method for determining the use safety value of the vehicle-mounted battery is: The deviation between the remaining power of the vehicle's onboard battery and a safety power threshold is used as a safety remaining power, and the power attenuation rate of the vehicle's onboard battery at different charge and discharge cycles is determined based on the usage cycle data of the vehicle's onboard battery. Determining an attenuation evaluation value of the on-board battery based on an average value of the battery charge attenuation rate and the number of charge and discharge cycles in which the battery charge attenuation rate is greater than a preset attenuation rate, and determining whether the on-board battery has an aging problem based on the attenuation evaluation value. If so, proceeding to the next step; if not, determining a safety value for the on-board battery based on the safe remaining power; An aging assessment value of the on-board battery is determined based on the number of usage cycles of the on-board battery and the charge and discharge depths and attenuation assessment values ​​at different usage cycles, and the safe remaining power is corrected based on the aging assessment value to obtain a safety value for the on-board battery.

6. The sentry warning method based on image recognition according to claim 1, characterized in that: The method for determining the traffic busyness during the parking period is: The flow evaluation value of the current location during the parking periods on different dates is determined by the vehicle flow and pedestrian flow during the parking periods on different dates at the current location, and the maximum value of the flow evaluation value is used as a reference evaluation value. The number of dates whose deviation from the reference evaluation value is less than a preset deviation is used to determine whether the accuracy of the reference evaluation value meets the requirements. If so, the reference evaluation value is used as the flow busyness of the parking period. If not, the flow busyness of the parking period is determined by the average value of the reference evaluation value.

7. The sentry warning method based on image recognition according to claim 1, characterized in that: Determining whether the traffic congestion meets the requirement based on the usage safety value specifically includes: The busyness threshold of the vehicle in different parking periods is determined by using the safety value, and when the traffic busyness is greater than the busyness threshold, it is determined that the traffic busyness does not meet the requirement.

8. The sentry warning method based on image recognition according to claim 1, characterized in that: The method for determining the problem probability of the parking period is: The vehicle parked in sentry mode at the current location within a recent preset parking period is used as a parking monitoring vehicle, and the number of historical alarms of the parking monitoring vehicle is determined based on the historical alarm data of the parking monitoring vehicle. Whether the number of historical alarms is within a preset number requirement range is determined based on the number of parking monitoring vehicles. If so, the probability of a problem in the parking period is determined based on the historical alarm number and the number of parking monitoring vehicles. If not, proceed to the next step. The percentage of dates on which the parking monitoring vehicle has historical alarm data within a preset time period is calculated based on the historical alarm data of the parking monitoring vehicle, and it is determined whether the percentage of dates on which the historical alarm data has historical alarm data is less than a preset ratio. If so, the probability of a problem in the parking period is determined based on the percentage of dates on which the parking monitoring vehicle has historical alarm data within the preset time period. If not, the process proceeds to the next step. The date on which the parking monitoring vehicle has historical alarm data within a preset time period is used as the alarm date, and problem assessment amounts are determined for different alarm dates based on the number of parking monitoring vehicles and the number of historical alarms on different alarm dates, and serious problem dates and general problem dates are determined among the alarm dates based on the problem assessment amounts; The number and proportion of serious problem dates in the alarm dates are obtained, and the problem probability of the parking period is determined based on the number of alarm dates and the problem evaluation amount.

9. The sentry warning method based on image recognition according to claim 1, characterized in that: The method for determining the image monitoring frequency is: Determining the basic image monitoring frequency of the sentinel warning mode during the parking period based on the safety value of the on-board battery, and judging whether the problem probability is greater than a preset probability value; if so, determining the image monitoring frequency of the sentinel warning mode based on the basic image monitoring frequency; if not, proceeding to the next step; The frequency correction amount is determined by the problem probability and the historical traffic busyness, and the image monitoring frequency of the sentinel warning mode during the parking period is determined based on the product of the frequency correction amount and the basic image monitoring frequency.

10. A sentry warning system based on image recognition, using the sentry warning method based on image recognition according to any one of claims 1 to 9, characterized in that: Specifically include: Battery evaluation module, busyness evaluation module, warning mode determination module, warning mode adjustment module; The battery evaluation module is responsible for obtaining the remaining power and safe power threshold of the vehicle's onboard battery, and determining the safety value of the onboard battery in combination with the cycle data; The busyness evaluation module is responsible for determining the parking period corresponding to the current moment, and determining the historical traffic busyness of the parking period based on the historical vehicle flow and historical pedestrian flow of the current location during parking periods on different dates; The warning mode determination module is responsible for determining the problem probability of the parking period by using the vehicles parked in the sentinel warning mode at the current location within the most recent preset parking period and historical alarm data, and determining the image monitoring frequency of the sentinel warning mode during the parking period based on the safety value of the vehicle battery, the problem probability, and the historical traffic congestion; The warning mode adjustment module is responsible for performing vehicle environment monitoring based on the image monitoring frequency to obtain an environmental image, and dynamically adjusting the image monitoring frequency of the sentry warning mode based on the recognition result of the environmental image during the parking period.

Images